Results 151 to 160 of about 14,332 (195)

Text intelligent correction in English translation: A study on integrating models with dependency attention mechanism. [PDF]

PLoS One
Liu Y, Zhang S.
europepmc   +1 more source

DEMINERS enables clinical metagenomics and comparative transcriptomic analysis by increasing throughput and accuracy of nanopore direct RNA sequencing. [PDF]

Genome Biol
Song J, Lin LA, Tang C, Chen C, Yang Q, Zhang D, Zhao Y, Wei HC, Linghu K, Xu Z, Chen T, He Z, Liu D, Zhong Y, Zhu W, Zeng W, Chen L, Song G, Chen M, Jiang J, Zhou J, Wang J, Chen B, Ying B, Wang Y, Geng J, Lin JW, Chen L.   +27 more
europepmc   +1 more source

Computational Neuroscience's Influence on Autism Neuro-Transmission Research: Mapping Serotonin, Dopamine, GABA, and Glutamate. [PDF]

Biomedicines
Bamicha V, Pergantis P, Skianis C, Drigas A.   +3 more
europepmc   +1 more source

Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks [PDF]

, 2005
openaire  

Probabilistic ASR Feature Extraction Applying Context-Sensitive Connectionist Temporal Classification Networks

, 2012
openaire   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Chinese Audio Transcription Using Connectionist Temporal Classification

Proceedings of the 8th International Conference on Computer and Communications Management, 2020
Mandarin is one of the global languages that have large users and speakers. There are several important factors for learners to be an expert in Mandarin. To be able to communicate properly, mastery in Chinese character (hanzi) and pīnyīn are required. We develop an Android-based app to help students who learn Mandarin.
null Jansen, Dyah E. Herwindiati, Janson Hendryli   +2 more
openaire   +1 more source

Connectionist temporal classification

Proceedings of the 23rd international conference on Machine learning - ICML '06, 2006
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is transcribed into words or sub-word units. Recurrent neural networks (RNNs) are powerful sequence learners that would seem well suited to such tasks.
Alex Graves, Santiago Fernández, Faustino Gomez, Jürgen Schmidhuber   +3 more
openaire   +1 more source

Sampled Connectionist Temporal Classification

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
This article introduces and evaluates Sampled Connectionist Temporal Classification (CTC) which connects the CTC criterion to the Cross Entropy (CE) objective through sampling. Instead of computing the logarithm of the sum of the alignment path likelihoods, at each training step the sampled CTC only computes the CE loss between the sampled alignment ...
Ehsan Variani, Tom Bagby, Kamel Lahouel, Erik McDermott, Michiel Bacchiani   +4 more
openaire   +1 more source

Multi-label Connectionist Temporal Classification

2019 International Conference on Document Analysis and Recognition (ICDAR), 2019
The Connectionist Temporal Classification (CTC) loss function [1] enables end-to-end training of a neural network for sequence-to-sequence tasks without the need for prior alignments between the input and output. CTC is traditionally used for training sequential, single-label problems; each element in the sequence has only one class.
Curtis Wigington, Brian Price, Scott Cohen   +2 more
openaire   +1 more source

Variational Connectionist Temporal Classification

2020
Connectionist Temporal Classification (CTC) is a training criterion designed for sequence labelling problems where the alignment between the inputs and the target labels is unknown. One of the key steps is to add a blank symbol to the target vocabulary. However, CTC tends to output spiky distributions since it prefers to output blank symbol most of the
Linlin Chao, Jingdong Chen, Wei Chu
openaire   +1 more source